INDEX

Explanations

words related to creative direction and industries, particularly in the context of media and writing

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 VÃ¡c

-0.16

esimal

-0.15

unday

-0.15

ape

-0.15

arnation

-0.14

Qed

-0.14

iconductor

-0.14

ardo

-0.14

iete

-0.14

duino

-0.14

POSITIVE LOGITS

anca

0.16

UID

0.15

ä¼į

0.14

athe

0.14

utters

0.14

 Interview

0.14

eson

0.13

ghi

0.13

aver

0.13

kol

0.13

Activations Density 0.037%

words related to creative direction and industries, particularly in the context of media and writing

No Comments

No Known Activations